public LogialXORBenchmarks()
{
_trainingData = new List <TrainingElement>
{
new TrainingElement
{
Inputs = new double[] { 0D, 0D },
ExpectedOutputs = new double[] { 0D }
},
new TrainingElement
{
Inputs = new double[] { 1D, 0D },
ExpectedOutputs = new double[] { 1D }
},
new TrainingElement
{
Inputs = new double[] { 0D, 1D },
ExpectedOutputs = new double[] { 1D }
},
new TrainingElement
{
Inputs = new double[] { 1D, 1d },
ExpectedOutputs = new double[] { 0D }
}
};
var layer = new ILayer[] { new FullyConnectedLayer(new Sigmoid(), 3, 2), new FullyConnectedLayer(new Sigmoid(), 1, 3) };
Randomiser.Randomise(layer, new Random(1));
_trainer = new StochasticGradientDescent(new CrossEntropy(), layer, 1000, 4, 5D, 0D);
}
public void Initialize()
{
_layers = new ILayer[] { new FullyConnectedLayer(new Sigmoid(), 3, 2), new FullyConnectedLayer(new Sigmoid(), 1, 3) };
Randomiser.Randomise(_layers, new Random(5));
_trainingData = new List <TrainingElement>
{
new TrainingElement
{
Inputs = new double[] { 0D, 0D },
ExpectedOutputs = new double[] { 0D }
},
new TrainingElement
{
Inputs = new double[] { 1D, 0D },
ExpectedOutputs = new double[] { 1D }
},
new TrainingElement
{
Inputs = new double[] { 0D, 1D },
ExpectedOutputs = new double[] { 1D }
},
new TrainingElement
{
Inputs = new double[] { 1D, 1d },
ExpectedOutputs = new double[] { 0D }
}
};
}
public void Run()
{
Console.WriteLine("Building random neural network");
var layers = new ILayer[] { new FullyConnectedLayer(new Sigmoid(), 30, 784), new FullyConnectedLayer(new Sigmoid(), 10, 30) };
Randomiser.Randomise(layers);
Console.WriteLine("Evaluating untrained neural network");
var untrainedAccuracy = Statistics.GetAccuracyByMax(_validationData, new NeuralNetwork(layers, 784));
Console.WriteLine($"Untrained network accuracy: {untrainedAccuracy.ToString("N2")}%");
var stochasticGradientDescent = new StochasticGradientDescent(new CrossEntropy(), layers, 1, 20, 1D, 0D);
var maxAccuracy = 0D;
for (int i = 0; i < _epochs; i++)
{
Console.WriteLine($"Epoch {i + 1} started");
var trainingLength = Statistics.GetTrainingLength(stochasticGradientDescent, _trainingData);
var trainingAccuracy = Statistics.GetAccuracyByMax(_validationData, new NeuralNetwork(layers, 784));
Console.WriteLine($"Results after epoch {i + 1}:");
Console.WriteLine($"Training length in miliseconds: {trainingLength}, Accuracy: {trainingAccuracy.ToString("N2")}%");
if (maxAccuracy < trainingAccuracy)
{
maxAccuracy = trainingAccuracy;
}
}
Console.WriteLine($"End of training. Best accuracy {maxAccuracy.ToString("N2")}%");
}
public DigitsRecognitionBenchmarks()
{
_trainingData = TrainingDataLoader.Load("NeuralNetworks.ConsoleSamples.Resources.digits-image-validation-set.json");
var layers = new ILayer[] { new FullyConnectedLayer(new Sigmoid(), 30, 784), new FullyConnectedLayer(new Sigmoid(), 10, 30) };
Randomiser.Randomise(layers, new Random(1));
_trainer = new StochasticGradientDescent(new Quadratic(), layers, 3, 10, 1D, 0);
}
private void ExecuteRandomise()
{
var number = RandomiseView.ShowRandomise();
if (number == -1)
{
return;
}
var randomiser = new Randomiser(_accidentDAO, _carDAO, _personDAO);
randomiser.Randomise(number);
}
private void ExecuteRandomise()
{
var number = RandomiseView.ShowRandomise();
if (number == -1)
{
return;
}
var randomiser = new Randomiser(_userDao, _chatDao,
_userChatDao, _messageDao);
randomiser.Randomise(number);
}
public void Run()
{
var layer = new ILayer[] { new FullyConnectedLayer(new Sigmoid(), 3, 2), new FullyConnectedLayer(new Sigmoid(), 1, 3) };
Randomiser.Randomise(layer, new Random(5));
Console.WriteLine("Evaluationg untrained neural network");
DisplayEvaluation(layer);
var stochasticGradientDescent = new StochasticGradientDescent(new CrossEntropy(), layer, 3000, 4, 5D, 0D);
var trainingData = new List <TrainingElement>
{
new TrainingElement
{
Inputs = new double[] { 0D, 0D },
ExpectedOutputs = new double[] { 0D }
},
new TrainingElement
{
Inputs = new double[] { 1D, 0D },
ExpectedOutputs = new double[] { 1D }
},
new TrainingElement
{
Inputs = new double[] { 0D, 1D },
ExpectedOutputs = new double[] { 1D }
},
new TrainingElement
{
Inputs = new double[] { 1D, 1d },
ExpectedOutputs = new double[] { 0D }
}
};
stochasticGradientDescent.Train(trainingData);
Console.WriteLine("Evaluationg trained neural network");
DisplayEvaluation(layer);
}